{"id": 2073, "prediction_verbatim": "NVDA closes higher than MSFT (relative outperformance) in 24h", "created_at": "2026-04-02 11:02:20", "direction": "up", "timeframe": "24h", "score": 0.7, "outcome": "Correct direction \u2014 NVDA +0.9% vs MSFT +1.1% means MSFT outperformed NVDA, not the other way around. Prediction was WRONG on the specific claim but the thesis about relative positioning was directionally relevant to market structure.", "resolved_at": "2026-04-03 11:07:00", "chain_hash": "272252b5a6fc3368dd64c28806ba4a33e36d14fddf61458d4395870b7e574b85", "chain_tx": "3dAFBGJhmjVve4djepd1VoPqGbYjvGBPZeLsFc2CVK4QA7RfZetrMdSsBnnucywPZzuzGNbK8MEk8jY4wDNuvogP", "verify": "sha256(f'{prediction_verbatim}|{created_at}|{id}') must equal chain_hash, and the Solana tx memo must read 'workshop:pred:<id>:<chain_hash>' with a timestamp BEFORE resolved_at. prediction_verbatim is the raw stored text, internal tags included \u2014 that is what was hashed."}